Corpus ID: 202719573

Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

@article{Marcheggiani2019GraphCO,
  title={Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling},
  author={Diego Marcheggiani and Ivan Titov},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.09814}
}
  • Diego Marcheggiani, Ivan Titov
  • Published in ArXiv 2019
  • Computer Science
  • Semantic role labeling (SRL) is the task of identifying predicates and labeling argument spans with semantic roles. Even though most semantic-role formalisms are built upon constituent syntax and only syntactic constituents can be labeled as arguments (e.g., FrameNet and PropBank), all the recent work on syntax-aware SRL relies on dependency representations of syntax. In contrast, we show how graph convolutional networks (GCNs) can be used to encode constituent structures and inform an SRL… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 47 REFERENCES

    Syntactic Scaffolds for Semantic Structures

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep contextualized word representations

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Layer Normalization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    The Proposition Bank: An Annotated Corpus of Semantic Roles

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Long Short-Term Memory

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL